While natural language processing systems often focus on a single language, multilingual transfer learning has the potential to improve performance, especially for low-resource languages. We introduce XLDA, cross-lingual data augmentation, a method that replaces a segment of the input text with its translation in another language. XLDA enhances performance of all 14 tested languages of the cross-lingual natural language inference (XNLI) benchmark. With improvements of up to $4.8\%$, training with XLDA achieves state-of-the-art performance for Greek, Turkish, and Urdu. XLDA is in contrast to, and performs markedly better than, a more naive approach that aggregates examples in various languages in a way that each example is solely in one language. On the SQuAD question answering task, we see that XLDA provides a $1.0\%$ performance increase on the English evaluation set. Comprehensive experiments suggest that most languages are effective as cross-lingual augmentors, that XLDA is robust to a wide range of translation quality, and that XLDA is even more effective for randomly initialized models than for pretrained models.

Microsoft Research Asia (MSRA) has achieved eight top places in the recent machine translation challenge organized by the 2019 fourth Conference on Machine Translation (WMT19), out of the eleven tasks it undertook. Overall, there are nineteen machine translation categories in WMT this year. MSRA achieved first place in machine translation tasks for Chinese-English, English-Finnish, English-German, English-Lithuanian, French-German, German-English, German-French and Russian-English. Three other tasks were placed second in their respective categories, which included English-Kazakh, Finnish-English and Lithuanian-English. As one of the leading machine translation competition globally, WMT is a platform for leading researchers to demonstrate their solutions, as well as to understand the continuous evolvement of machine translation technology. Now in its 14th year, more than 50 teams globally from technology companies, leading academic institutions and universities participated in a bid to demonstrate their machine translation capabilities.

The new system, dubbed the Translatotron, has three components, all of which look at the speaker's audio spectrogram--a visual snapshot of the frequencies used when the sound is playing, often called a voiceprint. The first component uses a neural network trained to map the audio spectrogram in the input language to the audio spectrogram in the output language. The second converts the spectrogram into an audio wave that can be played.

Google AI yesterday released its latest research result in speech-to-speech translation, the futuristic-sounding "Translatotron." Billed as the world's first end-to-end speech-to-speech translation model, Translatotron promises the potential for real-time cross-linguistic conversations with low latency and high accuracy. Humans have always dreamed of a voice-based device that could enable them to simply leap over language barriers. While advances in deep learning have contributed to highly improved accuracy in speech recognition and machine translation, smooth conversations between different language speakers remained hampered by unnatural pauses during machine processing. Google's wireless headphone Pixel Bud released in 2017 boasted real-time speech translation, but users found the practical experience less then satisfying.

On Wednesday, Google unveiled Translatotron, an in-development speech-to-speech translation system. It's not the first system to translate speech from one language to another, but Google designed Translatotron to do something other systems can't: retain the original speaker's voice in the translated audio. In other words, the tech could make it sound like you're speaking a language you don't know -- a remarkable step forward on the path to breaking down the global language barrier. According to Google's AI blog, most speech-to-speech translation systems follow a three-step process. First they transcribe the speech.

Google Translate is one of the company's most used products. It helps people translate one language to another through typing, taking pics of text, and using speech-to-text technology. Now, the company's launching a new project called Translatotron, which will offer direct speech-to-speech translations – without even using any text. In a post on Google's AI blog, the team behind the tool explained that instead of using speech-to-text and then text-to-speech to convert voice, it relied on a new model (which runs on a neural network) to develop the new system. Get 50% off tickets if you buy now.

Part of its success is due to its ability to model called Sequential Transformer capture long term dependencies. This is achieved (Vaswani et al., 2017). A Transformer is by taking long sequences as inputs and explicitly made of a sequence of layers that are composed of compute the relations between every token via a a block of parallel self-attention layers followed mechanism called the "self-attention" layer (Al-by a feedforward network. We refer to Vaswani Rfou et al., 2019).

The sequence-to-sequence (seq2seq) model for neural machine translation has significantly improved the accuracy of language translation. There have been new efforts to use this seq2seq model for program language translation or program comparisons. In this work, we present the detailed steps of using a seq2seq model to translate CUDA programs to OpenCL programs, which both have very similar programming styles. Our work shows (i) a training input set generation method, (ii) pre/post processing, and (iii) a case study using Polybench-gpu-1.0, NVIDIA SDK, and Rodinia benchmarks.

We present the first automatic emotion detection system for Cantonese. This system classifies input text into eight emotion classes: expectancy, joy, love, surprise, anxiety, sorrow, angry, or hate. While a number of emotion corpora and lexica for Mandarin Chinese have been developed, no emotion dataset is available for Cantonese. We leverage existing Mandarin Chinese emotion resources to build the system, with support from Cantonese-Mandarin lexical mappings from a machine translation system, as well as English-Mandarin lexical mappings to handle code-switching in Cantonese input. Evaluation on a set of Cantonese sentences from social media shows promising results.

Existing approaches to neural machine translation (NMT) generate the target language sequence token by token from left to right. However, this kind of unidirectional decoding framework cannot make full use of the target-side future contexts which can be produced in a right-to-left decoding direction, and thus suffers from the issue of unbalanced outputs. In this paper, we introduce a synchronous bidirectional neural machine translation (SB-NMT) that predicts its outputs using left-to-right and right-to-left decoding simultaneously and interactively, in order to leverage both of the history and future information at the same time. Specifically, we first propose a new algorithm that enables synchronous bidirectional decoding in a single model. Then, we present an interactive decoding model in which left-to-right (right-to-left) generation does not only depend on its previously generated outputs, but also relies on future contexts predicted by right-to-left (left-to-right) decoding. We extensively evaluate the proposed SB-NMT model on large-scale NIST Chinese-English, WMT14 English-German, and WMT18 Russian-English translation tasks. Experimental results demonstrate that our model achieves significant improvements over the strong Transformer model by 3.92, 1.49 and 1.04 BLEU points respectively, and obtains the state-of-the-art performance on Chinese-English and English-German translation tasks.